The Comparison of Individual Cat Recognition Using Neural Networks

TL;DR

This study systematically compares various neural network architectures for individual cat recognition, revealing that traditional CNNs with transfer learning outperform other models and highlighting the potential of ConvNeXt and DenseNet for practical applications.

Contribution

It provides a comparative analysis of neural networks for cat recognition, identifying the most effective models and suggesting practical improvements for pet management and wildlife monitoring.

Findings

Traditional CNNs with transfer learning outperform other models.

ConvNeXt and DenseNet show promising results for further optimization.

The study offers insights for improving cat identification in real-world settings.

Abstract

Facial recognition using deep learning has been widely used in social life for applications such as authentication, smart door locks, and photo grouping, etc. More and more networks have been developed to facilitate computer vision tasks, such as ResNet, DenseNet, EfficientNet, ConvNeXt, and Siamese networks. However, few studies have systematically compared the advantages and disadvantages of such neural networks in identifying individuals from images, especially for pet animals like cats. In the present study, by systematically comparing the efficacy of different neural networks in cat recognition, we found traditional CNNs trained with transfer learning have better performance than models trained with the fine-tuning method or Siamese networks in individual cat recognition. In addition, ConvNeXt and DenseNet yield significant results which could be further optimized for individual cat recognition in pet stores and in the wild. These results provide a method to improve cat management in pet stores and monitoring of cats in the wild.